# As a condition of accessing this website, you agree to abide by the following
# content signals:

# (a)  If a Content-Signal = yes, you may collect content for the corresponding
#      use.
# (b)  If a Content-Signal = no, you may not collect content for the
#      corresponding use.
# (c)  If the website operator does not include a Content-Signal for a
#      corresponding use, the website operator neither grants nor restricts
#      permission via Content-Signal with respect to the corresponding use.

# The content signals and their meanings are:

# search:   building a search index and providing search results (e.g., returning
#           hyperlinks and short excerpts from your website's contents). Search does not
#           include providing AI-generated search summaries.
# ai-input: inputting content into one or more AI models (e.g., retrieval
#           augmented generation, grounding, or other real-time taking of content for
#           generative AI search answers).
# ai-train: training or fine-tuning AI models.
# use:      how AI systems may consume the content (immediate, reference, or full).

# ANY RESTRICTIONS EXPRESSED VIA CONTENT SIGNALS ARE EXPRESS RESERVATIONS OF
# RIGHTS UNDER ARTICLE 4 OF THE EUROPEAN UNION DIRECTIVE 2019/790 ON COPYRIGHT
# AND RELATED RIGHTS IN THE DIGITAL SINGLE MARKET.

# BEGIN Cloudflare Managed content

User-agent: *
Content-Signal: search=yes,ai-train=no,use=reference
Allow: /

User-agent: Amazonbot
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: CloudflareBrowserRenderingCrawler
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: GPTBot
Disallow: /

User-agent: meta-externalagent
Disallow: /

# END Cloudflare Managed Content

# Lumify Robots.txt
# Lumify — the agent-ready Sports Intelligence API (https://lumify.ai)

User-agent: *
Allow: /

# Sitemap location — the only directive above that crawlers actually parse.
Sitemap: https://lumify.ai/sitemap.xml

# LLM-readable documentation (informational only — "LLMs:" is not a
# standard robots.txt directive; crawlers ignore it, so these are kept
# as comments rather than pseudo-directives).
# LLMs:      https://lumify.ai/llms.txt
# LLMs-full: https://lumify.ai/llms-full.txt

# AI agent discovery (also listed in sitemap.xml)
# Manifest:  https://lumify.ai/.well-known/agent.json
# OpenAPI:   https://lumify.ai/openapi.json
# MCP:       https://lumify.ai/mcp
# AI setup:  https://lumify.ai/docs/ai

# Block legacy WordPress URLs (site migrated from WordPress)
Disallow: /knowledgebase-category/
Disallow: /knowledgebase-tag/
Disallow: /tag/
Disallow: /category/
Disallow: /feed/
Disallow: /*/feed/
Disallow: /wp-content/
Disallow: /wp-includes/
Disallow: /wp-admin/

# Block Cloudflare internal paths
Disallow: /cdn-cgi/

# Block URLs with query parameters (prevents duplicate content from tracking
# params). NOTE: this is intentionally broad — any future public, indexable
# route that relies on a query string (rather than a path segment) will be
# blocked too. Re-check this rule before shipping such a route.
Disallow: /*?*

# Block authenticated app pages (require login)
Disallow: /app/
Disallow: /admin/

# Block login/logout pages
Disallow: /login
Disallow: /logout

# Block utility/health check endpoints
Disallow: /health
Disallow: /health-check

# Block API endpoints from indexing
Disallow: /api/

# Block auth flow confirmation pages
Disallow: /verify-email
Disallow: /verify-beta
Disallow: /beta-confirmation
Disallow: /reset-password
Disallow: /forgot-password
Disallow: /register

# ---------------------------------------------------------------------------
# AI crawlers — explicitly welcomed. Lumify is built to be read by agents.
# Named blocks mirror the same disallow rules as User-agent: * above (a named
# User-agent block replaces the wildcard block for that bot rather than
# combining with it, so the rules must be repeated here).
# ---------------------------------------------------------------------------

User-agent: GPTBot
User-agent: ChatGPT-User
User-agent: OAI-SearchBot
User-agent: ClaudeBot
User-agent: anthropic-ai
User-agent: PerplexityBot
User-agent: CCBot
Allow: /
Disallow: /knowledgebase-category/
Disallow: /knowledgebase-tag/
Disallow: /tag/
Disallow: /category/
Disallow: /feed/
Disallow: /*/feed/
Disallow: /wp-content/
Disallow: /wp-includes/
Disallow: /wp-admin/
Disallow: /cdn-cgi/
Disallow: /*?*
Disallow: /app/
Disallow: /admin/
Disallow: /login
Disallow: /logout
Disallow: /health
Disallow: /health-check
Disallow: /api/
Disallow: /verify-email
Disallow: /verify-beta
Disallow: /beta-confirmation
Disallow: /reset-password
Disallow: /forgot-password
Disallow: /register

# Google-Extended doesn't crawl independently — it's a Google-specific opt-in
# token controlling use of Googlebot-crawled content for AI training (Gemini).
User-agent: Google-Extended
Allow: /